© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201138
    Prev
    Next
    INDEX
    Explanations

    shiny product presentations

    np_acts-logits-general · gemini-2.5-flash-lite

    GitOps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ية
    0.54
    ክ
    0.50
     ganhar
    0.49
    حم
    0.48
     Hinweis
    0.48
    자
    0.47
    ال
    0.46
    йт
    0.46
     Apica
    0.46
     Başkanı
    0.46
    POSITIVE LOGITS
    ttier
    0.49
     thermostat
    0.49
    bati
    0.48
     restitution
    0.47
     geos
    0.45
     vestib
    0.45
     समझाने
    0.43
     thermostats
    0.43
    acci
    0.42
     によ
    0.42
    Activations Density 0.000%

    No Known Activations